Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.5926. Min Act: -0.1700
Data Index: 7291903 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.5613. Min Act: -0.1700
Data Index: 6569002 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4988. Min Act: -0.1700
Data Index: 5075355 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4676. Min Act: -0.1700
Data Index: 4913663 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4676. Min Act: -0.1700
Data Index: 1945548 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4676. Min Act: -0.1700
Data Index: 4113704 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4363. Min Act: -0.1700
Data Index: 3545541 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4363. Min Act: -0.1700
Data Index: 4238621 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4051. Min Act: -0.1700
Data Index: 6631913 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3738. Min Act: -0.1700
Data Index: 1457514 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3426. Min Act: -0.1700
Data Index: 2381943 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.4051. Min Act: -0.1700
Data Index: 577370 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3738. Min Act: -0.1700
Data Index: 8552437 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3426. Min Act: -0.1700
Data Index: 5923513 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3426. Min Act: -0.1700
Data Index: 4926639 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3738. Min Act: -0.1700
Data Index: 124105 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3426. Min Act: -0.1700
Data Index: 5876118 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3113. Min Act: -0.1700
Data Index: 68717 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3113. Min Act: -0.1700
Data Index: 4798007 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5926. Min Range: -5.5926
Max Act: 5.3113. Min Act: -0.1700
Data Index: 1445197 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19